Recovering shear stiffness degradation curves from classification data with a neural network approach
Recovering shear stiffness degradation curves from classification data with a neural network approach
Shear stiffness is critical in assessing the stress–strain response of geotechnical infrastructure, and is a complex, nonlinear parameter. Existing methods characterise stiffness degradation as a function of strain and require either bespoke laboratory element tests, or adoption of a curve fitting approach, based on an existing data set of laboratory element tests. If practitioners lack the required soil classification parameters, they are unable to use these curve fitting functions. Within this study, we examine the ability and versatility of an artificial neural network (ANN), in this case a feedforward multilayer perceptron, to predict strain-based stiffness degradation on the data set of element test results and soil classification data that underpins current curve fitting functions. It is shown that the ANN gives similar or better results to the existing curve fitting method when the same parameters are used, but also that the ANN approach enables curves to be recovered with ‘any’ subset of the considered soil classification parameters, providing practitioners with a great versatility to derive a stiffness degradation curve. A user-friendly and freely available graphical calculation app that implements the proposed methodology is also presented.
Design tool, Neural networks, Sands, Stiffness degradation
5619-5633
Charles, Jared A.
ff218ed7-09b0-4a1d-87d2-a54d8fbd1a3f
Gourvenec, Susan
6ff91ad8-1a91-42fe-a3f4-1b5d6f5ce0b8
Vardy, Mark E.
8dd019dc-e57d-4b49-8f23-0fa6d246e69d
October 2023
Charles, Jared A.
ff218ed7-09b0-4a1d-87d2-a54d8fbd1a3f
Gourvenec, Susan
6ff91ad8-1a91-42fe-a3f4-1b5d6f5ce0b8
Vardy, Mark E.
8dd019dc-e57d-4b49-8f23-0fa6d246e69d
Charles, Jared A., Gourvenec, Susan and Vardy, Mark E.
(2023)
Recovering shear stiffness degradation curves from classification data with a neural network approach.
Acta Geotechnica, 18 (10), .
(doi:10.1007/s11440-023-01879-4).
Abstract
Shear stiffness is critical in assessing the stress–strain response of geotechnical infrastructure, and is a complex, nonlinear parameter. Existing methods characterise stiffness degradation as a function of strain and require either bespoke laboratory element tests, or adoption of a curve fitting approach, based on an existing data set of laboratory element tests. If practitioners lack the required soil classification parameters, they are unable to use these curve fitting functions. Within this study, we examine the ability and versatility of an artificial neural network (ANN), in this case a feedforward multilayer perceptron, to predict strain-based stiffness degradation on the data set of element test results and soil classification data that underpins current curve fitting functions. It is shown that the ANN gives similar or better results to the existing curve fitting method when the same parameters are used, but also that the ANN approach enables curves to be recovered with ‘any’ subset of the considered soil classification parameters, providing practitioners with a great versatility to derive a stiffness degradation curve. A user-friendly and freely available graphical calculation app that implements the proposed methodology is also presented.
Text
s11440-023-01879-4
- Version of Record
More information
Accepted/In Press date: 24 March 2023
Published date: October 2023
Additional Information:
Funding Information:
The first and second authors are supported by the Royal Academy of Engineering under the Chairs in Emerging Technologies scheme. The work presented forms part of the activities of the Royal Academy of Engineering Chair in Emerging Technologies Centre of Excellence for Intelligent and Resilient Ocean Engineering and Supergen ORE Hub (Grant EPSRC EP/S000747/1). The authors acknowledge Professor Sadik Oztoprak for generously sharing his database of sand and gravel stiffness degradation curves as presented by Oztoprak and Bolton [] with us, and further for agreeing for the reformatted data set to be shared publicly so the geotechnical community can benefit from it.
Publisher Copyright:
© 2023, The Author(s).
Keywords:
Design tool, Neural networks, Sands, Stiffness degradation
Identifiers
Local EPrints ID: 481227
URI: http://eprints.soton.ac.uk/id/eprint/481227
ISSN: 1861-1125
PURE UUID: f753327e-8857-4b49-85f1-5ffcc4abd1b4
Catalogue record
Date deposited: 18 Aug 2023 17:08
Last modified: 18 Mar 2024 03:57
Export record
Altmetrics
Contributors
Author:
Mark E. Vardy
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
